基于图像处理的车牌定位及字符识别算法研究  

A Study on Algorithm of License Plate Positioning and Character Recognition Based on Image Processing

作　　者：张婷曼[1] 闫文耀[1] 王庆[2] 

机构地区：[1]延安大学西安创新学院,西安710100 [2]西安理工大学自动化与信息工程学院,西安710048

出　　处：《现代雷达》2014年第8期26-30,共5页Modern Radar

基　　金：陕西省教育厅专项科研计划资助项目(2013JK1120)

摘　　要：为了更好地在车辆行驶过程中清晰识别车辆牌照,文中采用了中值滤波的方法,平滑处理彩色车辆,利用Prewitt算子进行检测,提取出图像的车牌边缘,按照车牌的不同特征,最终准确的提取出车牌的范围。字符分割时,灰度化与二值化彩色的车辆图像,位置不正的车牌图像进行矫正处理,去除车牌的边框,提取车牌上的单个字符,统一归化,细致处理,最后提取字符的骨架,进行数据处理。文中主要采用的是Visual C++6.0的方法进行车牌的定位,字符分割的算法进行编程,通过实践,表明该算法在车辆图像的定位与字符分割的处理上具有速度快、准确率高的优点。In this paper, median filtering method is used for smooth processing of color vehicle in order to achieve better recogni- tion of license plate of moving vehicle. By utilization of Prewitt operator for detection, the image at the edge of the license plate is extracted and its final accurate range can be gotten according to different characteristics of the license. During character segmenta- tion, graying and binaryzation is performed on vehicle image. Through correction of image misregistration along with frame removal of license plate, the individual characters on it are extracted. Then, unification of domestication and fine treatment is carried out to finally extract the skeleton of the character for data processing. Visual C＋＋ 6.0 is used as main programming tool for the algorithms of license plate positioning and character segmentation. A lot of practice shows that the proposed algorithm has the advantages of high speed and high accuracy in localization of the vehicle image and processing of character segmentation.

关 键 词：图像处理 车牌定位 字符识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]